Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SEDONA-708] Sedona should use PyArrow to get GeoPandas #1794

Merged
merged 4 commits into from
Feb 7, 2025
Merged

[SEDONA-708] Sedona should use PyArrow to get GeoPandas #1794

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6392dbd
Initial commit
jiayuasu Feb 6, 2025
a8d6f5b
Separate the logic between Pandas and GeoPandas
jiayuasu Feb 7, 2025
c5524cd
Work with GeoPandas < 1.0.0
jiayuasu Feb 7, 2025
e5bace2
Refine the code structure
jiayuasu Feb 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions python/sedona/maps/SedonaMapUtils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
import json

from sedona.sql.types import GeometryType
from sedona.utils.geoarrow import dataframe_to_arrow
from packaging.version import parse


class SedonaMapUtils:
Expand All @@ -34,17 +36,25 @@ def __convert_to_gdf_or_pdf__(cls, df, rename=True, geometry_col=None):
"""
if geometry_col is None:
geometry_col = SedonaMapUtils.__get_geometry_col__(df)
pandas_df = df.toPandas()

# Convert the dataframe to arrow format, then to geopandas dataframe
# This is faster than converting directly to geopandas dataframe via toPandas
if (
geometry_col is None
): # No geometry column found even after searching schema, return Pandas Dataframe
return pandas_df
data_pyarrow = dataframe_to_arrow(df)
return data_pyarrow.to_pandas()
try:
import geopandas as gpd
except ImportError:
msg = "GeoPandas is missing. You can install it manually or via apache-sedona[kepler-map] or apache-sedona[pydeck-map]."
raise ImportError(msg) from None
geo_df = gpd.GeoDataFrame(pandas_df, geometry=geometry_col)
# From GeoPandas 1.0.0 onwards, the from_arrow method is available
if parse(gpd.__version__) >= parse("1.0.0"):
data_pyarrow = dataframe_to_arrow(df)
geo_df = gpd.GeoDataFrame.from_arrow(data_pyarrow)
else:
geo_df = gpd.GeoDataFrame(df.toPandas(), geometry=geometry_col)
if geometry_col != "geometry" and rename is True:
geo_df.rename_geometry("geometry", inplace=True)
return geo_df
Expand Down
5 changes: 4 additions & 1 deletion python/sedona/raster_utils/SedonaUtils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,13 @@
# specific language governing permissions and limitations
# under the License.

from sedona.maps.SedonaMapUtils import SedonaMapUtils


class SedonaUtils:
@classmethod
def display_image(cls, df):
from IPython.display import HTML, display

display(HTML(df.toPandas().to_html(escape=False)))
pdf = SedonaMapUtils.__convert_to_gdf_or_pdf__(df, rename=False)
display(HTML(pdf.to_html(escape=False)))
Loading